Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7663
    Prev
    Next
    INDEX
    Explanations

    key moments of dialogue and dramatic tension within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )++;
    -0.87
     Signalez
    -0.73
    KommentareTeilen
    -0.71
    óta
    -0.69
    давно
    -0.68
    AndroidJUnit
    -0.66
    WebVitals
    -0.65
    isiaj
    -0.62
    __':
    
    -0.62
    CloseOperation
    -0.62
    POSITIVE LOGITS
     midway
    1.93
     halfway
    1.78
     mid
    1.45
     early
    1.32
     late
    1.25
    early
    1.14
     Midway
    1.09
    後半
    1.04
    mid
    1.04
     באמצ
    1.04
    Activations Density 0.478%

    No Known Activations